用本体约束生成医学摘要，减少幻觉并提升领域相关性。
Ontology-Constrained Generation of Domain-Specific Clinical Summaries
- 通过本体引导的约束解码，确保摘要符合医学领域规范。
- 在MIMIC-III数据集上显著降低幻觉，提升摘要与专科内容的相关性。
- 适合医疗文本生成、电子病历摘要等临床场景使用。
大型语言模型（LLMs）为文本摘要提供了有前景的解决方案，但某些领域要求摘要中必须包含特定信息。生成这类领域适配的摘要仍是开放挑战。同时，当前方法存在幻觉问题，阻碍实际部署。本文提出一种新方法，利用本体生成结构化与非结构化领域适配摘要。采用本体引导的约束解码过程，在减少幻觉的同时提升内容相关性。应用于医疗领域时，该方法可有效总结不同专科的电子健康记录（EHRs），帮助医生聚焦关键信息。在MIMIC-III数据集上的评估表明，该方法在生成领域适配的临床笔记摘要方面表现更优，并有效降低幻觉。
原文摘要 · Abstract (English)
Large Language Models (LLMs) offer promising solutions for text summarization. However, some domains require specific information to be available in the summaries. Generating these domain-adapted summaries is still an open challenge. Similarly, hallucinations in generated content is a major drawback of current approaches, preventing their deployment. This study proposes a novel approach that leverages ontologies to create domain-adapted summaries both structured and unstructured. We employ an ontology-guided constrained decoding process to reduce hallucinations while improving relevance. When applied to the medical domain, our method shows potential in summarizing Electronic Health Records (EHRs) across different specialties, allowing doctors to focus on the most relevant information to their domain. Evaluation on the MIMIC-III dataset demonstrates improvements in generating domain-adapted summaries of clinical notes and hallucination reduction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。